Show simple item record

dc.contributor.authorHammer, Hugo Lewien_US
dc.contributor.authorYazidi, Anisen_US
dc.contributor.authorBai, Aleksanderen_US
dc.contributor.authorEngelstad, Paal E.en_US
dc.date.accessioned2016-03-22T08:19:08Z
dc.date.available2016-03-22T08:19:08Z
dc.date.issued2015en_US
dc.identifier.citationHammer, H., Yazidi, A., Bai, A., & Engelstad, P. (2015). Building Domain Specific Sentiment Lexicons Combining Information from Many Sentiment Lexicons and a Domain Specific Corpus. In A. Amine, L. Bellatreche, Z. Elberrichi, J. E. Neuhold, & R. Wrembel (Eds.), Computer Science and Its Applications: 5th IFIP TC 5 International Conference, CIIA 2015, Saida, Algeria, May 20-21, 2015, Proceedings (pp. 205-216). Cham: Springer International Publishing.en_US
dc.identifier.isbn978-3-319-19577-3en_US
dc.identifier.issn1868-4238en_US
dc.identifier.otherFRIDAID 1249311en_US
dc.identifier.urihttp://hdl.handle.net/10642/3175
dc.description.abstractMost approaches to sentiment analysis requires a sentiment lexicon in order to automatically predict sentiment or opinion in a text. The lexicon is generated by selecting words and assigning scores to the words, and the performance the sentiment analysis depends on the quality of the assigned scores. This paper addresses an aspect of sentiment lexicon generation that has been overlooked so far; namely that the most appropriate score assigned to a word in the lexicon is dependent on the domain. The common practice, on the contrary, is that the same lexicon is used without adjustments across different domains ignoring the fact that the scores are normally highly sensitive to the domain. Consequently, the same lexicon might perform well on a single domain while performing poorly on another domain, unless some score adjustment is performed. In this paper, we advocate that a sentiment lexicon needs some further adjustments in order to perform well in a specific domain. In order to cope with these domain specific adjustments, we adopt a stochastic formulation of the sentiment score assignment problem instead of the classical deterministic formulation. Thus, viewing a sentiment score as a stochastic variable permits us to accommodate to the domain specific adjustments. Experimental results demonstrate the feasibility of our approach and its superiority to generic lexicons without domain adjustments.en_US
dc.language.isoengen_US
dc.publisherSpringeren_US
dc.relation.ispartofseriesComputer Science and Its Applications: 5th IFIP TC 5 International Conference, CIIA 2015, Saida, Algeria, May 20-21, 2015, Proceedings;en_US
dc.subjectBayesian decision theoryen_US
dc.subjectCross-domainen_US
dc.subjectSentiment classificationen_US
dc.subjectSentiment lexiconen_US
dc.subjectVDP::Matematikk og Naturvitenskap: 400::Matematikk: 410::Anvendt matematikk: 413en_US
dc.subjectVDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550::Annen informasjonsteknologi: 559en_US
dc.titleBuilding domain specific sentiment lexicons combining information from many sentiment lexicons and a domain specific corpusen_US
dc.typePeer revieweden_US
dc.typeChapteren_US
dc.description.versionThe final publication is available at Springer via http://dx.doi.org/20.1007/978-3-319-19578-0_17
dc.identifier.doihttp://dx.doi.org/20.1007/978-3-319-19578-0_17


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record